Learning Cardiac Features: ECG Biometrics Across Time and~Exercise· 跨时间和运动的心电图特征学习
Electrocardiograms (ECGs) carry subject-specific patterns enabling reliable individual discrimination, forming the basis of ECG biometrics. Beyond authentication, this paradigm holds significant potential to secure sensitive cardiac data and to serve as a pretext task in self-supervised learning. Yet, most studies remain confined to singlesession, resting data, leaving robustness to temporal and physiological variations largely untested. We address this gap by evaluating ECG biometrics under realistic conditions involving exercise-induced stress and cross-session variability. A Siamese ResNet with late multi-lead fusion strategy is trained on a large ECG dataset extracted from cardiopulmonary exercise tests and evaluated with a exercise-and time-aware protocol, as well as on public benchma
心电图生物特征在不同时间和运动状态下的鲁棒性研究。
- 核心方法
- 提出了一种基于Siamese ResNet的心电图生物特征模型，采用后期多导联融合策略，利用从心肺运动测试中提取的大规模心电图数据进行训练，并通过特定协议评估。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 大多心里生物特征研究仅限于单次静息状态下的数据，缺乏对时间及生理变化影响的测试。
- 关键实验
- 在大规模心肺运动测试数据集上进行了训练，并使用了公开基准数据集进行验证，实验设计考虑了时间和运动因素。
- 主要贡献
- 首次系统评估了心电图生物特征在运动引起的压力和跨会话变化中的表现。
- 意义与局限
- 扩展了心电图生物特征的应用场景，提高了其在实际条件下的可靠性。但模型的泛化能力和实时监测性能仍需进一步研究。